© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31648
    Prev
    Next
    INDEX
    Explanations

    services and phenomena

    np_acts-logits-general · gemini-2.5-flash-lite

    topic followed by specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    0.46
    劳动
    0.39
     commandBuffer
    0.37
     چیر
    0.37
    여러
    0.36
     první
    0.35
     bipartite
    0.35
    ستی
    0.34
     kumpulan
    0.34
     اینکه
    0.34
    POSITIVE LOGITS
    ä
    0.45
     通常
    0.43
     is
    0.41
     =
    0.40
     occupies
    0.40
    <%@
    0.40
     중요하다
    0.39
    em
    0.39
     affects
    0.39
     proportionally
    0.39
    Activations Density 0.027%

    No Known Activations